Official benchmarks map / BRIGHT

Who is #1 on BRIGHT?

FINAL-Bench/Darwin-BRIGHT-Retriever is ranked first on the BRIGHT leaderboard with 0.31, 179.1% ahead of mteb/baseline-bm25s. Read live from the Hugging Face API on November 8, 2026.

Field: Retrieval. 2 leaderboard entries. Figures read from the Hugging Face API on November 8, 2026 and refreshed daily.

Top 2

#ModelOrganizationScore
1FINAL-Bench/Darwin-BRIGHT-RetrieverFINAL-Bench0.31
2mteb/baseline-bm25smteb0.11

About this board

BRIGHT is a dataset that Hugging Face marks as an official benchmark. Its leaderboard is built automatically from the .eval_results files that model repositories publish, so entries are mostly self-reported by model authors and evaluation settings differ between submissions. A verified tag appears only where Hugging Face marks an entry as verified.

Original board: huggingface.co/datasets/mteb/BRIGHT

Other official benchmarks

hlecwe-benchgpqatyped-decisionsphysical-engineerings-last-examSWE-bench_Verifieddecision-index-leaderboardopen-asr-leaderboardolmOCR-benchdeep-swesafeagents-judge-benchMMLU-Proapex-agentsagents-last-exam

Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.